A method of performing real-time ship conflict probability ranking in open waters based on AIS data

Abstract

In this paper, an AIS-based real-time conflict probability (RtCP) ranking method is proposed for maritime autonomous surface ships (MASS). This approach is applicable to the decision-support stage of the first degrees of autonomy (DoA1) of MASS, which is combined with expert systems determination for collision avoidance. To provide accurate conflict probability level (CPL) of encountering ships in real time, a safety-distance influence indicator composed of the real-time factors of ship maneuverability such as speed and course angle is proposed. This indicator is combined with a data-driven risk assessment algorithm to quantify the probability of collisions, and classifies the CPL by analyzing a large amount of historical AIS data. As a result, it provides basis for real-time CPL determination under actual shipping conditions. To illustrate the effectiveness of the proposed indicator, the RtCP model was applied to traffic data in the northern Baltic Sea with many validity tests. These tests suggest that the RtCP model is adequate for ranking and prioritizing encounter conflict probability in real time, and it provides collision avoidance decision support for onboard seafarers of MASS. Moreover, a comparative analysis of encounter cases shows that the proposed model has superior results and a greater applicability in terms of classification of CPL for an open sea area over other methods.